The idea of an 8-bit floating point number sounds kinda crazy at first, but they come in handy in applications where you don't need much precision and you're memory constrained. Comparing IEEE-like numbers and posit numbers.| John D. Cook
Posit numbers make more efficient use of the bits representing real numbers than do conventional IEEE floating point numbers. This post explains what posits are, how their bits are interpreted, their dynamic range, etc.| John D. Cook
How the bits of a floating point number are organized, how (de)normalization works, etc.| John D. Cook